ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems · HackerPapers discussions

ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems — mentioned by therobots927

Thu, 09 Jul 2026 02:19:30 GMT

I was meaning to imply that yes assuming we had a proportionate amount of birdsong data, would we be able to reverse engineer their flight abilities. I think given the fact that spatial reasoning is nearly universal among species, we can very safely assume that it is “too evolutionary old and too low-level, too far removed from higher cognition, to leak into language heavily” I think this is pretty apparent. It’s very rare for athletes to talk through their actions in high level detail - I saw the ball coming towards me at a 37 degree phi 23 degree epsilon angle at a speed of approximately 20…

Paper and discussion history. A mention is not an endorsement.

ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems — mentioned by westurner

Sun, 27 Jul 2025 16:47:50 GMT

"ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems" (2025) https://arxiv.org/abs/2505.11831 ARC Prize: $1m: https://arcprize.org/ : > At ARC Prize, our mission is to serve as a North Star towards AGI through enduring benchmarks, directing efforts towards systems capable of general intelligence and significantly compressing the timeline for scientific breakthroughs ARC-AGI-3: Interactive Reasoning Benchmark (2026) https://arcprize.org/arc-agi/3/ : > The first eval that measures human-like intelligence in AI. [w/ HuggingFace]

Paper and discussion history. A mention is not an endorsement.

ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems — mentioned by yorwba

Thu, 12 Jun 2025 10:25:10 GMT

The ARC-AGI-2 paper https://arxiv.org/pdf/2505.11831#figure.4 uses a non-representative sample, success rate differs widely across participants and "final ARC-AGI-2 test pairs were solved, on average, by 75% of people who attempted them. The average test-taker solved 66% of tasks they attempted. 100% of ARC-AGI-2 tasks were solved by at least two people (many were solved by more) in two attempts or less." Certainly those non-representative humans are much better than current models, but they're also far from scoring 100%.

Paper and discussion history. A mention is not an endorsement.